Borrowing it
Nothing to install: this file belongs to S1M0N38/pi-voice. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/S1M0N38/pi-voice/main/.agents/skills/pi-test/SKILL.mdgit clone --depth 1 https://github.com/S1M0N38/pi-voiceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/s1m0n38/pi-voice/pi-test)<a href="https://agentmods.dev/skills/s1m0n38/pi-voice/pi-test"><img src="https://agentmods.dev/badge/skills/s1m0n38/pi-voice/pi-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/s1m0n38/pi-voice/pi-test"><img src="https://agentmods.dev/badge/skills/s1m0n38/pi-voice/pi-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00123 | $0.01415 |
| Opus 5.5 | $0.00049 | $0.00566 |
| Sonnet 5.5 | $0.00025 | $0.00283 |
| Haiku 4.5 | $0.00012 | $0.00142 |
Grade B, and why
pi-test scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| Model not loaded | `curl -X POST http://127.0.0.1:8181/models/download -d '{"dtype":"q4"}'` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://127.0.0.1:8181/health # verify model is loaded How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi-voice E2E Testing with Pilotty
Test pi-voice's extension stack (TUI, tts tool, auto-TTS) via PTY-based terminal automation.
Prerequisites
npm run server # start TTS server (default: 127.0.0.1:8181)
curl -sf http://127.0.0.1:8181/health # verify model is loaded
which pilotty # verify pilotty is installed
All tests require the server running with a loaded model before spawning pi.
Test Suites
| Script | What it tests | Run |
|---|---|---|
tests/tui.sh |
/voice command: navigate, toggle, cycle, reset, close | npm run test:tui |
tests/toggle.sh |
alt+v toggle: session-only override, status bar ♪ | npm run test:toggle |
tests/queue.sh |
Playback queue: tool + auto-TTS audio never overlap | npm run test:queue |
tests/run.sh |
All three suites | npm run test:e2e |
Test Architecture
tests/helpers.sh— shared utilities: assertions, pilotty wrappers, session lifecycle, server checks- Each test: sources helpers → spawns pi → interacts → asserts → cleans up
- Config is backed up and restored around each test to avoid side effects
queue.shpolls afplay PIDs to detect overlapping playback
Core Workflow
Every test follows this pattern:
source "$(dirname "$0")/helpers.sh" # load utilities
require_server # verify server + model
# ... backup config ...
spawn_pi # pilotty spawn --name ... --cwd "$PACKAGE_DIR"
wait_for_pi # wait for [Skills] indicator
HASH=$(snapshot_content_hash)
send_type "/voice"
send_key Enter
TEXT=$(await_change_and_snapshot_text "$HASH" 500 5000)
assert_match "description" "pattern" "$TEXT"
# ... interact ...
kill_session
# ... restore config ...
print_summary
Helper Functions (tests/helpers.sh)
Assertions
assert_match DESC PATTERN TEXT— grep for pattern in textassert_no_match DESC PATTERN TEXT— assert pattern absentassert_equals DESC EXPECTED ACTUAL— exact string equalityassert_not_empty DESC VALUE— value is non-empty
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 152 lines · 123 tokens per session scan B ce1fa73336c8
pi-test is a skill published in the GitHub repository S1M0N38/pi-voice (6 stars, last pushed 2mo ago), licensed MIT. It adds 123 tokens to every session and 1,415 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.